INDEX

Explanations

proper nouns and phrases related to the creation of things

oai_token-act-pair · gpt-3.5-turbo

instances of the word "created"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SPONSORED

-0.68

pled

-0.67

ingly

-0.67

ãģĦ

-0.62

ledge

-0.61

 clipboard

-0.60

pert

-0.59

perty

-0.59

hom

-0.58

isite

-0.58

POSITIVE LOGITS

ĸļ

0.75

âĶģ

0.74

by

0.74

ynamic

0.71

 collabor

0.71

monton

0.69

emis

0.67

utsche

0.66

romeda

0.65

tern

0.65

Activations Density 0.155%

proper nouns and phrases related to the creation of things

instances of the word "created"

No Comments

No Known Activations